Głębokie modele dyskryminacyjne w wykrywaniu amyloidowych motywów sygnałowych
[Deep discriminative models in the detection of amyloid signaling motifs]

Krzysztof Pysz (*) 
(Department of Biomedical Engineering, PWr, Wrocław)


Amyloid signaling sequences adopt the cross-β fold that is capable of 
self-replication in the templating process. Propagation of the amyloid fold 
from the receptor to the effector protein is used for signal transduction in 
the immune response pathways in animals, fungi and bacteria. So far, a dozen 
families of amyloid signaling motifs (ASMs) have been classified. 
Unfortunately, due to the wide variety of ASMs it is difficult to identify 
them in large protein databases available today, which limits the 
possibility of conducting experimental studies. To date, many different deep 
learning (DL) models were used in a range of tasks regarding proteins, such 
as family classification, structure prediction and protein-protein 
interaction. In this work, we apply tailor-made bidirectional LSTM and 
BERT-based architectures to modeling ASMs and compare their performance to a 
state-of-the-art machine learning grammatical model. Our research is focused 
on developing a discriminative model of generalized amyloid signaling 
motifs, capable of detecting ASMs in large data sets. The DL-based models 
are trained on a diverse set of motif families and a global negative set, 
and used to identify ASMs from remotely related families. We investigate the 
differences in data representation in both models in order to identify 
potentially amyloidogenic fragments and find that our DL-based models are 
well suited for ASM detection tasks and often outperform the previously used 
grammatical model.

(*) Joint work with Jakub Gałązka and Witold Dyrka